size mismatch for pos_embed: copying a param with shape torch.Size([1, 197, 768]) from checkpoint, the shape in current model is torch.Size([1, 99, 768]).

[nasseralfadly]

RuntimeError: Error(s) in loading state_dict for VisionTransformer: Missing key(s) in state_dict: "blocks1.0.norm1.weight", "blocks1.0.norm1.bias", "blocks1.0.attn.qkv.weight", "blocks1.0.attn.qkv.bias", "blocks1.0.attn.proj.weight", "blocks1.0.attn.proj.bias", "blocks1.0.norm2.weight", "blocks1.0.norm2.bias", "blocks1.0.mlp.fc1.weight", "blocks1.0.mlp.fc1.bias", "blocks1.0.mlp.fc2.weight", "blocks1.0.mlp.fc2.bias", "blocks1.1.norm1.weight", "blocks1.1.norm1.bias", "blocks1.1.attn.qkv.weight", "blocks1.1.attn.qkv.bias", "blocks1.1.attn.proj.weight", "blocks1.1.attn.proj.bias", "blocks1.1.norm2.weight", "blocks1.1.norm2.bias", "blocks1.1.mlp.fc1.weight", "blocks1.1.mlp.fc1.bias", "blocks1.1.mlp.fc2.weight", "blocks1.1.mlp.fc2.bias", "blocks1.2.norm1.weight", "blocks1.2.norm1.bias", "blocks1.2.attn.qkv.weight", "blocks1.2.attn.qkv.bias", "blocks1.2.attn.proj.weight", "blocks1.2.attn.proj.bias", "blocks1.2.norm2.weight", "blocks1.2.norm2.bias", "blocks1.2.mlp.fc1.weight", "blocks1.2.mlp.fc1.bias", "blocks1.2.mlp.fc2.weight", "blocks1.2.mlp.fc2.bias", "blocks1.3.norm1.weight", "blocks1.3.norm1.bias", "blocks1.3.attn.qkv.weight", "blocks1.3.attn.qkv.bias", "blocks1.3.attn.proj.weight", "blocks1.3.attn.proj.bias", "blocks1.3.norm2.weight", "blocks1.3.norm2.bias", "blocks1.3.mlp.fc1.weight", "blocks1.3.mlp.fc1.bias", "blocks1.3.mlp.fc2.weight", "blocks1.3.mlp.fc2.bias", "blocks1.4.norm1.weight", "blocks1.4.norm1.bias", "blocks1.4.attn.qkv.weight", "blocks1.4.attn.qkv.bias", "blocks1.4.attn.proj.weight", "blocks1.4.attn.proj.bias", "blocks1.4.nor... Unexpected key(s) in state_dict: "blocks.0.norm1.bias", "blocks.0.norm1.weight", "blocks.0.norm2.bias", "blocks.0.norm2.weight", "blocks.0.mlp.fc1.bias", "blocks.0.mlp.fc1.weight", "blocks.0.mlp.fc2.bias", "blocks.0.mlp.fc2.weight", "blocks.0.attn.proj.bias", "blocks.0.attn.proj.weight", "blocks.0.attn.qkv.bias", "blocks.0.attn.qkv.weight", "blocks.1.norm1.bias", "blocks.1.norm1.weight", "blocks.1.norm2.bias", "blocks.1.norm2.weight", "blocks.1.mlp.fc1.bias", "blocks.1.mlp.fc1.weight", "blocks.1.mlp.fc2.bias", "blocks.1.mlp.fc2.weight", "blocks.1.attn.proj.bias", "blocks.1.attn.proj.weight", "blocks.1.attn.qkv.bias", "blocks.1.attn.qkv.weight", "blocks.10.norm1.bias", "blocks.10.norm1.weight", "blocks.10.norm2.bias", "blocks.10.norm2.weight", "blocks.10.mlp.fc1.bias", "blocks.10.mlp.fc1.weight", "blocks.10.mlp.fc2.bias", "blocks.10.mlp.fc2.weight", "blocks.10.attn.proj.bias", "blocks.10.attn.proj.weight", "blocks.10.attn.qkv.bias", "blocks.10.attn.qkv.weight", "blocks.11.norm1.bias", "blocks.11.norm1.weight", "blocks.11.norm2.bias", "blocks.11.norm2.weight", "blocks.11.mlp.fc1.bias", "blocks.11.mlp.fc1.weight", "blocks.11.mlp.fc2.bias", "blocks.11.mlp.fc2.weight", "blocks.11.attn.proj.bias", "blocks.11.attn.proj.weight", "blocks.11.attn.qkv.bias", "blocks.11.attn.qkv.weight", "blocks.2.norm1.bias", "blocks.2.norm1.weight", "blocks.2.norm2.bias", "blocks.2.norm2.weight", "blocks.2.mlp.fc1.bias", "blocks.2.mlp.fc1.weight", "blocks.2.mlp.fc2.bias", "blocks.2.mlp.fc2.weight",... size mismatch for pos_embed: copying a param with shape torch.Size([1, 197, 768]) from checkpoint, the shape in current model is torch.Size([1, 99, 768]).